ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
FoundationPose
Model
NVIDIA
NVIDIA
FoundationPose

6-DoF object pose estimation and tracking, providing the object pose and 3D bounding box

1 Version
deployable_v1.0Selected
08/23/2024 1:02 AM UTC125.95 MBBatch Size: 1GPU: V100
SHA256 digests
KeyValue
refiner_net.onnx4a4445d2506b1bfc0a8d62fa80f8780a7e37bb0df13bb09aa5dd04a03bf0c954
score_net.onnxbb7208919557560ecb0e10a30612821f0025a2578190b17677bdf3653514a48d
TAO Toolkit API
KeyValue
is_backboneFalse
endpoints['foundationpose']
format_version0.0.1
model_formatonnx
tao_version['>=5.5.0']
trainableFalse
TAO Toolkit UI Metadata
KeyValue
licenseNVAIE EULA
taskobject pose estimation
format_version0.0.1
backbone_typecnn
domainpurpose-built
accuracy83.3%
num_parameters32.53M
backbone_classresnet